An Efficient Method for Detecting Dense and Small Objects in UAV Images
Object detection in unmanned aerial vehicle (UAV) images is an important and challenging task for many applications, which often needs highly efficient detection algorithms to meet the accuracy and real-time requirements of the applications. In this article, we investigate efficient mechanisms for d...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10460088/ |
| _version_ | 1797243317956640768 |
|---|---|
| author | Chenyang Li Suiping Zhou Hang Yu Tianxiang Guo Yuru Guo Jichen Gao |
| author_facet | Chenyang Li Suiping Zhou Hang Yu Tianxiang Guo Yuru Guo Jichen Gao |
| author_sort | Chenyang Li |
| collection | DOAJ |
| description | Object detection in unmanned aerial vehicle (UAV) images is an important and challenging task for many applications, which often needs highly efficient detection algorithms to meet the accuracy and real-time requirements of the applications. In this article, we investigate efficient mechanisms for detecting dense and small objects in UAV images. Specifically, 1) kernel K-means is used to obtain optimal anchors for dense and small object detection; 2) a spatial information enhancement module is proposed to improve the detection accuracy of dense objects by extracting object spatial location information; 3) a Coord_C3 module is proposed to improve the receptive field of the network and to reduce the number of network parameters; and 4) a small detection head is added in the Head of the network and skip connections are employed in the Neck of the network to improve the detection accuracy of small objects. Experimental results on the VisDrone-2019, LEVIR-ship, and Stanford Drone datasets show that our method not only has higher detection accuracy but also runs faster compared to state-of-the-art detection methods. |
| first_indexed | 2024-04-24T18:53:12Z |
| format | Article |
| id | doaj.art-ac4f3a0e1bae4bef9ec16d724bbaf887 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-04-24T18:53:12Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-ac4f3a0e1bae4bef9ec16d724bbaf8872024-03-26T17:48:04ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352024-01-01176601661510.1109/JSTARS.2024.337323110460088An Efficient Method for Detecting Dense and Small Objects in UAV ImagesChenyang Li0https://orcid.org/0000-0002-5371-5574Suiping Zhou1https://orcid.org/0000-0003-0914-066XHang Yu2https://orcid.org/0000-0003-0914-066XTianxiang Guo3https://orcid.org/0009-0007-1799-8603Yuru Guo4https://orcid.org/0009-0003-5252-7939Jichen Gao5https://orcid.org/0009-0007-1924-5082School of Aerospace Science and Technology, Xidian University, Xi'an, ChinaSchool of Aerospace Science and Technology, Xidian University, Xi'an, ChinaSchool of Aerospace Science and Technology, Xidian University, Xi'an, ChinaSchool of Aerospace Science and Technology, Xidian University, Xi'an, ChinaSchool of Aerospace Science and Technology, Xidian University, Xi'an, ChinaSchool of Aerospace Science and Technology, Xidian University, Xi'an, ChinaObject detection in unmanned aerial vehicle (UAV) images is an important and challenging task for many applications, which often needs highly efficient detection algorithms to meet the accuracy and real-time requirements of the applications. In this article, we investigate efficient mechanisms for detecting dense and small objects in UAV images. Specifically, 1) kernel K-means is used to obtain optimal anchors for dense and small object detection; 2) a spatial information enhancement module is proposed to improve the detection accuracy of dense objects by extracting object spatial location information; 3) a Coord_C3 module is proposed to improve the receptive field of the network and to reduce the number of network parameters; and 4) a small detection head is added in the Head of the network and skip connections are employed in the Neck of the network to improve the detection accuracy of small objects. Experimental results on the VisDrone-2019, LEVIR-ship, and Stanford Drone datasets show that our method not only has higher detection accuracy but also runs faster compared to state-of-the-art detection methods.https://ieeexplore.ieee.org/document/10460088/Deep learningkernel K-meansobject detectionspatial informationunmanned aerial vehicle (UAVs) |
| spellingShingle | Chenyang Li Suiping Zhou Hang Yu Tianxiang Guo Yuru Guo Jichen Gao An Efficient Method for Detecting Dense and Small Objects in UAV Images IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Deep learning kernel K-means object detection spatial information unmanned aerial vehicle (UAVs) |
| title | An Efficient Method for Detecting Dense and Small Objects in UAV Images |
| title_full | An Efficient Method for Detecting Dense and Small Objects in UAV Images |
| title_fullStr | An Efficient Method for Detecting Dense and Small Objects in UAV Images |
| title_full_unstemmed | An Efficient Method for Detecting Dense and Small Objects in UAV Images |
| title_short | An Efficient Method for Detecting Dense and Small Objects in UAV Images |
| title_sort | efficient method for detecting dense and small objects in uav images |
| topic | Deep learning kernel K-means object detection spatial information unmanned aerial vehicle (UAVs) |
| url | https://ieeexplore.ieee.org/document/10460088/ |
| work_keys_str_mv | AT chenyangli anefficientmethodfordetectingdenseandsmallobjectsinuavimages AT suipingzhou anefficientmethodfordetectingdenseandsmallobjectsinuavimages AT hangyu anefficientmethodfordetectingdenseandsmallobjectsinuavimages AT tianxiangguo anefficientmethodfordetectingdenseandsmallobjectsinuavimages AT yuruguo anefficientmethodfordetectingdenseandsmallobjectsinuavimages AT jichengao anefficientmethodfordetectingdenseandsmallobjectsinuavimages AT chenyangli efficientmethodfordetectingdenseandsmallobjectsinuavimages AT suipingzhou efficientmethodfordetectingdenseandsmallobjectsinuavimages AT hangyu efficientmethodfordetectingdenseandsmallobjectsinuavimages AT tianxiangguo efficientmethodfordetectingdenseandsmallobjectsinuavimages AT yuruguo efficientmethodfordetectingdenseandsmallobjectsinuavimages AT jichengao efficientmethodfordetectingdenseandsmallobjectsinuavimages |